Paper Group ANR 473
Dependency Parsing with LSTMs: An Empirical Evaluation. AdaNet: Adaptive Structural Learning of Artificial Neural Networks. Assisted Dictionary Learning for fMRI Data Analysis. Multi-Dueling Bandits and Their Application to Online Ranker Evaluation. Improved Sampling Techniques for Learning an Imbalanced Data Set. Statistical Meta-Analysis of Prese …
Dependency Parsing with LSTMs: An Empirical Evaluation
| Title | Dependency Parsing with LSTMs: An Empirical Evaluation |
| Authors | Adhiguna Kuncoro, Yuichiro Sawai, Kevin Duh, Yuji Matsumoto |
| Abstract | We propose a transition-based dependency parser using Recurrent Neural Networks with Long Short-Term Memory (LSTM) units. This extends the feedforward neural network parser of Chen and Manning (2014) and enables modelling of entire sequences of shift/reduce transition decisions. On the Google Web Treebank, our LSTM parser is competitive with the best feedforward parser on overall accuracy and notably achieves more than 3% improvement for long-range dependencies, which has proved difficult for previous transition-based parsers due to error propagation and limited context information. Our findings additionally suggest that dropout regularisation on the embedding layer is crucial to improve the LSTM’s generalisation. |
| Tasks | Dependency Parsing |
| Published | 2016-04-22 |
| URL | http://arxiv.org/abs/1604.06529v2 |
| http://arxiv.org/pdf/1604.06529v2.pdf | |
| PWC | https://paperswithcode.com/paper/dependency-parsing-with-lstms-an-empirical |
| Repo | |
| Framework | |
AdaNet: Adaptive Structural Learning of Artificial Neural Networks
| Title | AdaNet: Adaptive Structural Learning of Artificial Neural Networks |
| Authors | Corinna Cortes, Xavi Gonzalvo, Vitaly Kuznetsov, Mehryar Mohri, Scott Yang |
| Abstract | We present new algorithms for adaptively learning artificial neural networks. Our algorithms (AdaNet) adaptively learn both the structure of the network and its weights. They are based on a solid theoretical analysis, including data-dependent generalization guarantees that we prove and discuss in detail. We report the results of large-scale experiments with one of our algorithms on several binary classification tasks extracted from the CIFAR-10 dataset. The results demonstrate that our algorithm can automatically learn network structures with very competitive performance accuracies when compared with those achieved for neural networks found by standard approaches. |
| Tasks | |
| Published | 2016-07-05 |
| URL | http://arxiv.org/abs/1607.01097v3 |
| http://arxiv.org/pdf/1607.01097v3.pdf | |
| PWC | https://paperswithcode.com/paper/adanet-adaptive-structural-learning-of |
| Repo | |
| Framework | |
Assisted Dictionary Learning for fMRI Data Analysis
| Title | Assisted Dictionary Learning for fMRI Data Analysis |
| Authors | Manuel Morante Moreno, Yannis Kopsinis, Eleftherios Kofidis, Christos Chatzichristos, Sergios Theodoridis |
| Abstract | Extracting information from functional magnetic resonance (fMRI) images has been a major area of research for more than two decades. The goal of this work is to present a new method for the analysis of fMRI data sets, that is capable to incorporate a priori available information, via an efficient optimization framework. Tests on synthetic data sets demonstrate significant performance gains over existing methods of this kind. |
| Tasks | Dictionary Learning |
| Published | 2016-10-11 |
| URL | http://arxiv.org/abs/1610.03276v1 |
| http://arxiv.org/pdf/1610.03276v1.pdf | |
| PWC | https://paperswithcode.com/paper/assisted-dictionary-learning-for-fmri-data |
| Repo | |
| Framework | |
Multi-Dueling Bandits and Their Application to Online Ranker Evaluation
| Title | Multi-Dueling Bandits and Their Application to Online Ranker Evaluation |
| Authors | Brian Brost, Yevgeny Seldin, Ingemar J. Cox, Christina Lioma |
| Abstract | New ranking algorithms are continually being developed and refined, necessitating the development of efficient methods for evaluating these rankers. Online ranker evaluation focuses on the challenge of efficiently determining, from implicit user feedback, which ranker out of a finite set of rankers is the best. Online ranker evaluation can be modeled by dueling ban- dits, a mathematical model for online learning under limited feedback from pairwise comparisons. Comparisons of pairs of rankers is performed by interleaving their result sets and examining which documents users click on. The dueling bandits model addresses the key issue of which pair of rankers to compare at each iteration, thereby providing a solution to the exploration-exploitation trade-off. Recently, methods for simultaneously comparing more than two rankers have been developed. However, the question of which rankers to compare at each iteration was left open. We address this question by proposing a generalization of the dueling bandits model that uses simultaneous comparisons of an unrestricted number of rankers. We evaluate our algorithm on synthetic data and several standard large-scale online ranker evaluation datasets. Our experimental results show that the algorithm yields orders of magnitude improvement in performance compared to stateof- the-art dueling bandit algorithms. |
| Tasks | Online Ranker Evaluation |
| Published | 2016-08-22 |
| URL | http://arxiv.org/abs/1608.06253v1 |
| http://arxiv.org/pdf/1608.06253v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-dueling-bandits-and-their-application |
| Repo | |
| Framework | |
Improved Sampling Techniques for Learning an Imbalanced Data Set
| Title | Improved Sampling Techniques for Learning an Imbalanced Data Set |
| Authors | Maureen Lyndel C. Lauron, Jaderick P. Pabico |
| Abstract | This paper presents the performance of a classifier built using the stackingC algorithm in nine different data sets. Each data set is generated using a sampling technique applied on the original imbalanced data set. Five new sampling techniques are proposed in this paper (i.e., SMOTERandRep, Lax Random Oversampling, Lax Random Undersampling, Combined-Lax Random Oversampling Undersampling, and Combined-Lax Random Undersampling Oversampling) that were based on the three sampling techniques (i.e., Random Undersampling, Random Oversampling, and Synthetic Minority Oversampling Technique) usually used as solutions in imbalance learning. The metrics used to evaluate the classifier’s performance were F-measure and G-mean. F-measure determines the performance of the classifier for every class, while G-mean measures the overall performance of the classifier. The results using F-measure showed that for the data without a sampling technique, the classifier’s performance is good only for the majority class. It also showed that among the eight sampling techniques, RU and LRU have the worst performance while other techniques (i.e., RO, C-LRUO and C-LROU) performed well only on some classes. The best performing techniques in all data sets were SMOTE, SMOTERandRep, and LRO having the lowest F-measure values between 0.5 and 0.65. The results using G-mean showed that the oversampling technique that attained the highest G-mean value is LRO (0.86), next is C-LROU (0.85), then SMOTE (0.84) and finally is SMOTERandRep (0.83). Combining the result of the two metrics (F-measure and G-mean), only the three sampling techniques are considered as good performing (i.e., LRO, SMOTE, and SMOTERandRep). |
| Tasks | |
| Published | 2016-01-18 |
| URL | http://arxiv.org/abs/1601.04756v1 |
| http://arxiv.org/pdf/1601.04756v1.pdf | |
| PWC | https://paperswithcode.com/paper/improved-sampling-techniques-for-learning-an |
| Repo | |
| Framework | |
Statistical Meta-Analysis of Presentation Attacks for Secure Multibiometric Systems
| Title | Statistical Meta-Analysis of Presentation Attacks for Secure Multibiometric Systems |
| Authors | Battista Biggio, Giorgio Fumera, Gian Luca Marcialis, Fabio Roli |
| Abstract | Prior work has shown that multibiometric systems are vulnerable to presentation attacks, assuming that their matching score distribution is identical to that of genuine users, without fabricating any fake trait. We have recently shown that this assumption is not representative of current fingerprint and face presentation attacks, leading one to overestimate the vulnerability of multibiometric systems, and to design less effective fusion rules. In this paper, we overcome these limitations by proposing a statistical meta-model of face and fingerprint presentation attacks that characterizes a wider family of fake score distributions, including distributions of known and, potentially, unknown attacks. This allows us to perform a thorough security evaluation of multibiometric systems against presentation attacks, quantifying how their vulnerability may vary also under attacks that are different from those considered during design, through an uncertainty analysis. We empirically show that our approach can reliably predict the performance of multibiometric systems even under never-before-seen face and fingerprint presentation attacks, and that the secure fusion rules designed using our approach can exhibit an improved trade-off between the performance in the absence and in the presence of attack. We finally argue that our method can be extended to other biometrics besides faces and fingerprints. |
| Tasks | |
| Published | 2016-09-06 |
| URL | http://arxiv.org/abs/1609.01461v1 |
| http://arxiv.org/pdf/1609.01461v1.pdf | |
| PWC | https://paperswithcode.com/paper/statistical-meta-analysis-of-presentation |
| Repo | |
| Framework | |
Spatial Modeling of Oil Exploration Areas Using Neural Networks and ANFIS in GIS
| Title | Spatial Modeling of Oil Exploration Areas Using Neural Networks and ANFIS in GIS |
| Authors | Nouraddin Misagh, Mohammadreza Ashouri |
| Abstract | Exploration of hydrocarbon resources is a highly complicated and expensive process where various geological, geochemical and geophysical factors are developed then combined together. It is highly significant how to design the seismic data acquisition survey and locate the exploratory wells since incorrect or imprecise locations lead to waste of time and money during the operation. The objective of this study is to locate high-potential oil and gas field in 1: 250,000 sheet of Ahwaz including 20 oil fields to reduce both time and costs in exploration and production processes. In this regard, 17 maps were developed using GIS functions for factors including: minimum and maximum of total organic carbon (TOC), yield potential for hydrocarbons production (PP), Tmax peak, production index (PI), oxygen index (OI), hydrogen index (HI) as well as presence or proximity to high residual Bouguer gravity anomalies, proximity to anticline axis and faults, topography and curvature maps obtained from Asmari Formation subsurface contours. To model and to integrate maps, this study employed artificial neural network and adaptive neuro-fuzzy inference system (ANFIS) methods. The results obtained from model validation demonstrated that the 17x10x5 neural network with R=0.8948, RMS=0.0267, and kappa=0.9079 can be trained better than other models such as ANFIS and predicts the potential areas more accurately. However, this method failed to predict some oil fields and wrongly predict some areas as potential zones. |
| Tasks | |
| Published | 2016-08-21 |
| URL | http://arxiv.org/abs/1608.05934v1 |
| http://arxiv.org/pdf/1608.05934v1.pdf | |
| PWC | https://paperswithcode.com/paper/spatial-modeling-of-oil-exploration-areas |
| Repo | |
| Framework | |
Deep learning is competing random forest in computational docking
| Title | Deep learning is competing random forest in computational docking |
| Authors | Mohamed Khamis, Walid Gomaa, Basem Galal |
| Abstract | Computational docking is the core process of computer-aided drug design; it aims at predicting the best orientation and conformation of a small drug molecule when bound to a target large protein receptor. The docking quality is typically measured by a scoring function: a mathematical predictive model that produces a score representing the binding free energy and hence the stability of the resulting complex molecule. We analyze the performance of both learning techniques on the scoring power, the ranking power, docking power, and screening power using the PDBbind 2013 database. For the scoring and ranking powers, the proposed learning scoring functions depend on a wide range of features (energy terms, pharmacophore, intermolecular) that entirely characterize the protein-ligand complexes. For the docking and screening powers, the proposed learning scoring functions depend on the intermolecular features of the RF-Score to utilize a larger number of training complexes. For the scoring power, the DL_RF scoring function achieves Pearson’s correlation coefficient between the predicted and experimentally measured binding affinities of 0.799 versus 0.758 of the RF scoring function. For the ranking power, the DL scoring function ranks the ligands bound to fixed target protein with accuracy 54% for the high-level ranking and with accuracy 78% for the low-level ranking while the RF scoring function achieves (46% and 62%) respectively. For the docking power, the DL_RF scoring function has a success rate when the three best-scored ligand binding poses are considered within 2 \AA\ root-mean-square-deviation from the native pose of 36.0% versus 30.2% of the RF scoring function. For the screening power, the DL scoring function has an average enrichment factor and success rate at the top 1% level of (2.69 and 6.45%) respectively versus (1.61 and 4.84%) respectively of the RF scoring function. |
| Tasks | |
| Published | 2016-08-23 |
| URL | http://arxiv.org/abs/1608.06665v1 |
| http://arxiv.org/pdf/1608.06665v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-is-competing-random-forest-in |
| Repo | |
| Framework | |
Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks
| Title | Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks |
| Authors | Nicolas Usunier, Gabriel Synnaeve, Zeming Lin, Soumith Chintala |
| Abstract | We consider scenarios from the real-time strategy game StarCraft as new benchmarks for reinforcement learning algorithms. We propose micromanagement tasks, which present the problem of the short-term, low-level control of army members during a battle. From a reinforcement learning point of view, these scenarios are challenging because the state-action space is very large, and because there is no obvious feature representation for the state-action evaluation function. We describe our approach to tackle the micromanagement scenarios with deep neural network controllers from raw state features given by the game engine. In addition, we present a heuristic reinforcement learning algorithm which combines direct exploration in the policy space and backpropagation. This algorithm allows for the collection of traces for learning using deterministic policies, which appears much more efficient than, for example, {\epsilon}-greedy exploration. Experiments show that with this algorithm, we successfully learn non-trivial strategies for scenarios with armies of up to 15 agents, where both Q-learning and REINFORCE struggle. |
| Tasks | Q-Learning, Starcraft |
| Published | 2016-09-10 |
| URL | http://arxiv.org/abs/1609.02993v3 |
| http://arxiv.org/pdf/1609.02993v3.pdf | |
| PWC | https://paperswithcode.com/paper/episodic-exploration-for-deep-deterministic |
| Repo | |
| Framework | |
Video Interpolation using Optical Flow and Laplacian Smoothness
| Title | Video Interpolation using Optical Flow and Laplacian Smoothness |
| Authors | Wenbin Li, Darren Cosker |
| Abstract | Non-rigid video interpolation is a common computer vision task. In this paper we present an optical flow approach which adopts a Laplacian Cotangent Mesh constraint to enhance the local smoothness. Similar to Li et al., our approach adopts a mesh to the image with a resolution up to one vertex per pixel and uses angle constraints to ensure sensible local deformations between image pairs. The Laplacian Mesh constraints are expressed wholly inside the optical flow optimization, and can be applied in a straightforward manner to a wide range of image tracking and registration problems. We evaluate our approach by testing on several benchmark datasets, including the Middlebury and Garg et al. datasets. In addition, we show application of our method for constructing 3D Morphable Facial Models from dynamic 3D data. |
| Tasks | Optical Flow Estimation |
| Published | 2016-03-26 |
| URL | http://arxiv.org/abs/1603.08124v1 |
| http://arxiv.org/pdf/1603.08124v1.pdf | |
| PWC | https://paperswithcode.com/paper/video-interpolation-using-optical-flow-and |
| Repo | |
| Framework | |
Haze Visibility Enhancement: A Survey and Quantitative Benchmarking
| Title | Haze Visibility Enhancement: A Survey and Quantitative Benchmarking |
| Authors | Yu Li, Shaodi You, Michael S. Brown, Robby T. Tan |
| Abstract | This paper provides a comprehensive survey of methods dealing with visibility enhancement of images taken in hazy or foggy scenes. The survey begins with discussing the optical models of atmospheric scattering media and image formation. This is followed by a survey of existing methods, which are grouped to multiple image methods, polarizing filters based methods, methods with known depth, and single-image methods. We also provide a benchmark of a number of well known single-image methods, based on a recent dataset provided by Fattal and our newly generated scattering media dataset that contains ground truth images for quantitative evaluation. To our knowledge, this is the first benchmark using numerical metrics to evaluate dehazing techniques. This benchmark allows us to objectively compare the results of existing methods and to better identify the strengths and limitations of each method. |
| Tasks | |
| Published | 2016-07-21 |
| URL | http://arxiv.org/abs/1607.06235v1 |
| http://arxiv.org/pdf/1607.06235v1.pdf | |
| PWC | https://paperswithcode.com/paper/haze-visibility-enhancement-a-survey-and |
| Repo | |
| Framework | |
Non-Greedy L21-Norm Maximization for Principal Component Analysis
| Title | Non-Greedy L21-Norm Maximization for Principal Component Analysis |
| Authors | Feiping Nie, Heng Huang |
| Abstract | Principal Component Analysis (PCA) is one of the most important unsupervised methods to handle high-dimensional data. However, due to the high computational complexity of its eigen decomposition solution, it hard to apply PCA to the large-scale data with high dimensionality. Meanwhile, the squared L2-norm based objective makes it sensitive to data outliers. In recent research, the L1-norm maximization based PCA method was proposed for efficient computation and being robust to outliers. However, this work used a greedy strategy to solve the eigen vectors. Moreover, the L1-norm maximization based objective may not be the correct robust PCA formulation, because it loses the theoretical connection to the minimization of data reconstruction error, which is one of the most important intuitions and goals of PCA. In this paper, we propose to maximize the L21-norm based robust PCA objective, which is theoretically connected to the minimization of reconstruction error. More importantly, we propose the efficient non-greedy optimization algorithms to solve our objective and the more general L21-norm maximization problem with theoretically guaranteed convergence. Experimental results on real world data sets show the effectiveness of the proposed method for principal component analysis. |
| Tasks | |
| Published | 2016-03-28 |
| URL | http://arxiv.org/abs/1603.08293v1 |
| http://arxiv.org/pdf/1603.08293v1.pdf | |
| PWC | https://paperswithcode.com/paper/non-greedy-l21-norm-maximization-for |
| Repo | |
| Framework | |
Who Leads the Clothing Fashion: Style, Color, or Texture? A Computational Study
| Title | Who Leads the Clothing Fashion: Style, Color, or Texture? A Computational Study |
| Authors | Qin Zou, Zheng Zhang, Qian Wang, Qingquan Li, Long Chen, Song Wang |
| Abstract | It is well known that clothing fashion is a distinctive and often habitual trend in the style in which a person dresses. Clothing fashions are usually expressed with visual stimuli such as style, color, and texture. However, it is not clear which visual stimulus places higher/lower influence on the updating of clothing fashion. In this study, computer vision and machine learning techniques are employed to analyze the influence of different visual stimuli on clothing-fashion updates. Specifically, a classification-based model is proposed to quantify the influence of different visual stimuli, in which each visual stimulus’s influence is quantified by its corresponding accuracy in fashion classification. Experimental results demonstrate that, on clothing-fashion updates, the style holds a higher influence than the color, and the color holds a higher influence than the texture. |
| Tasks | |
| Published | 2016-08-26 |
| URL | http://arxiv.org/abs/1608.07444v1 |
| http://arxiv.org/pdf/1608.07444v1.pdf | |
| PWC | https://paperswithcode.com/paper/who-leads-the-clothing-fashion-style-color-or |
| Repo | |
| Framework | |
Efficient Volumetric Fusion of Airborne and Street-Side Data for Urban Reconstruction
| Title | Efficient Volumetric Fusion of Airborne and Street-Side Data for Urban Reconstruction |
| Authors | András Bódis-Szomorú, Hayko Riemenschneider, Luc Van Gool |
| Abstract | Airborne acquisition and on-road mobile mapping provide complementary 3D information of an urban landscape: the former acquires roof structures, ground, and vegetation at a large scale, but lacks the facade and street-side details, while the latter is incomplete for higher floors and often totally misses out on pedestrian-only areas or undriven districts. In this work, we introduce an approach that efficiently unifies a detailed street-side Structure-from-Motion (SfM) or Multi-View Stereo (MVS) point cloud and a coarser but more complete point cloud from airborne acquisition in a joint surface mesh. We propose a point cloud blending and a volumetric fusion based on ray casting across a 3D tetrahedralization (3DT), extended with data reduction techniques to handle large datasets. To the best of our knowledge, we are the first to adopt a 3DT approach for airborne/street-side data fusion. Our pipeline exploits typical characteristics of airborne and ground data, and produces a seamless, watertight mesh that is both complete and detailed. Experiments on 3D urban data from multiple sources and different data densities show the effectiveness and benefits of our approach. |
| Tasks | |
| Published | 2016-09-05 |
| URL | http://arxiv.org/abs/1609.01345v1 |
| http://arxiv.org/pdf/1609.01345v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-volumetric-fusion-of-airborne-and |
| Repo | |
| Framework | |
Methods for Sparse and Low-Rank Recovery under Simplex Constraints
| Title | Methods for Sparse and Low-Rank Recovery under Simplex Constraints |
| Authors | Ping Li, Syama Sundar Rangapuram, Martin Slawski |
| Abstract | The de-facto standard approach of promoting sparsity by means of $\ell_1$-regularization becomes ineffective in the presence of simplex constraints, i.e.,~the target is known to have non-negative entries summing up to a given constant. The situation is analogous for the use of nuclear norm regularization for low-rank recovery of Hermitian positive semidefinite matrices with given trace. In the present paper, we discuss several strategies to deal with this situation, from simple to more complex. As a starting point, we consider empirical risk minimization (ERM). It follows from existing theory that ERM enjoys better theoretical properties w.r.t.~prediction and $\ell_2$-estimation error than $\ell_1$-regularization. In light of this, we argue that ERM combined with a subsequent sparsification step like thresholding is superior to the heuristic of using $\ell_1$-regularization after dropping the sum constraint and subsequent normalization. At the next level, we show that any sparsity-promoting regularizer under simplex constraints cannot be convex. A novel sparsity-promoting regularization scheme based on the inverse or negative of the squared $\ell_2$-norm is proposed, which avoids shortcomings of various alternative methods from the literature. Our approach naturally extends to Hermitian positive semidefinite matrices with given trace. Numerical studies concerning compressed sensing, sparse mixture density estimation, portfolio optimization and quantum state tomography are used to illustrate the key points of the paper. |
| Tasks | Density Estimation, Portfolio Optimization, Quantum State Tomography |
| Published | 2016-05-02 |
| URL | http://arxiv.org/abs/1605.00507v1 |
| http://arxiv.org/pdf/1605.00507v1.pdf | |
| PWC | https://paperswithcode.com/paper/methods-for-sparse-and-low-rank-recovery |
| Repo | |
| Framework | |
